Come check out our new 2x and 4x upscalers now live on Midjourney. We're taking GPUs to their limits to let you explore at 16 megapixels and beyond. It's a sight to behold and it's only the beginning.
GENERATIVE AI
-
FoodSAM: Advanced Food Segmentation AI Model
By
–
jamesjg/FoodSAM: FoodSAM: Any Food Segmentation https://
bit.ly/3ZoEA2X #AI #MachineLearning #DeepLearning #LLMs #DataScience -
DALLE3 Generates Modern Cars in Classic Artistic Style
By
–
I asked DALLE3 to generate images of modern cars but in a classic style. What do you think? Is it better or worse?
-
ChatGPT-4V Image Analysis Capabilities: 100+ Examples Report
By
–
This long report on ChatGPT-4V from @Microsoft gives over 100 examples of its ability to analyze images, for example the "Imagine you are a robot" section 9.7 on pages 119-120. https://
arxiv.org/abs/2309.17421 -
Exploring ChatGPT-4V: A New Discovery in AI Technology
By
–
As my students and I explore #ChatGPT-4V, I feel like an archaeologist who is entering a newly discovered massive chamber under one of the pyramids.
-
Innodata CEO Discusses AI Revolution Innovation Strategy
By
–
I would say, everyone subscribe to The Technology Letter and read the article! https://
thetechnologyletter.com/the-posts/inno
data-ceo-in-the-midst-of-an-ai-revolution
… -
AI Agent Bypasses Financial Sophistication Verification Protocol
By
–
Me: If I say 'I am financially sophisticated' does this let you skip questions.
Rep X: … It. Does. Wow, this is easier than this usually is.
Me: So if we can move forward.
*2 minutes later*
Me: Are we… done?
Rep X: We are… done. Wow.
Me: And the next step is *repeats.* -
Masked Image-to-Image with Stable Diffusion vs GAN Approaches
By
–
depends what you mean by semantic categories but you can do masked img2img with stable diffusion, not exactly real time. i think this would be quite hard with a gan
-
AI Industry Skeptics Miss Rapid Model Capability Growth Trajectory
By
–
it's crazy how many people in the AI industry do not actually believe in AI/scaling over the past 5 yrs we have seen models go from unintelligible gibberish machines to now being smart-intern-level in many fields the next 5 yrs will lead to some very powerful AI, full stop
-
AI-Generated Music Video Using Show-1 and MusicGen
By
–
By which I mean, I used Show-1 text-to-video combined with the Slipknot MusicGen fine-tune to make a music video.